© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69530
    Prev
    Next
    INDEX
    Explanations

    hold on to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    朥
    -2.69
    焢
    -2.28
    　　　　　　
    -2.22
    獁
    -2.20
    ꯸
    -2.17
    猻
    -2.09
    r
    -2.03
    b
    -1.99
    　　　　　　　
    -1.99
    Зно
    -1.98
    POSITIVE LOGITS
    \
    2.50
     
    2.03
    owskiego
    1.92
     of
    1.90
    ();
    1.88
     =
    1.87
     impos
    1.85
    ."
    1.84
     impo
    1.83
    因而
    1.80
    Activations Density 0.003%

    No Known Activations